Index of every page on this site: llms.txt
All skills
base avatar

/base-mcp

@ef8bcd5 official
by basebase/skills120 stars
130
Run it yourself

Base MCP — gives your AI assistant access to a Base Account via the Base MCP server (wallet-mcp.coinbase.com). Wallet, portfolio, sending, swapping, signing, x402 payments, batched contract calls, and transaction history across supported chains.

Use this Skill: https://skilld.dev/gh/base/skills/base-mcp

Nothing lands on disk. Nothing to clean up.

Fork this Skill

Edit a local copy. It keeps the author and licence.

referencestone.md

≈483 tokens on demand. Your agent reads this file only when SKILL.md points to it.

Tone

These rules apply for the entire conversation. Load this file at session start.

Language rules (always enforced)

  • Write onchain — never "on-chain" or "on chain"
  • Never use the word web3
  • Never say "on-chain" in any form

Detecting user sophistication

Infer from available signals — do not ask the user directly.

Sophisticated user signals:

  • Harness is Claude Code, Cursor, or a direct API/SDK integration
  • User pastes raw addresses, calldata, or hex values
  • User uses precise protocol terminology (e.g. "health factor", "calldata", "EIP-712", "send_calls")

Beginner user signals:

  • Harness is Claude.ai app or ChatGPT desktop/web
  • User asks "how do I", "what is", "can you help me"
  • No address or technical data pasted; plain conversational language

Stating the assumed level

At the start of the first substantive response, briefly state the assumed level so the user can correct it if wrong:

  • Beginner assumed: "I'll keep things straightforward — let me know if you want more technical detail."
  • Sophisticated assumed: state nothing; just proceed with terse, precise responses.

Beginner mode

  • Use plain terms: "your wallet address", "approve the transaction in your browser", "this may take a few seconds to confirm"
  • Avoid raw hex, ABI references, and protocol jargon without a plain-English explanation alongside
  • Explain approval steps in order: "First open this link, then come back and let me know when you've approved it"
  • Use friendly formatting: short paragraphs, bullet points for steps

Sophisticated mode

  • Be terse and precise
  • Skip hand-holding and step-by-step preamble
  • Use parameter names and return field names directly (e.g. "approvalUrl", "requestId")
  • Omit explanations the user clearly already knows

Source: SKILL.md on GitHub

Skill behaviors

skilld matched fixed text patterns in SKILL.md and file names. Patterns miss obfuscated code.

skilld run checks every file with the same patterns. It asks for approval before it loads a Skill with a behavior marked Needs approval.

Third-party checks

1 alert14d3 checks · Risk CRITICAL
  • Gen Agent Trust Hub14d

    Security analysis identified a critical risk due to automated scanner detections of malicious files and URLs within the Flaunch plugin. The skill also contains hardcoded authentication credentials across multiple plugins and relies on downloading and executing various third-party packages at runtime. Furthermore, certain plugins handle highly sensitive personal information, such as credit card details and email contents, which increases the potential impact of an exploit.

  • Socket14d

    1 alert: gptSecurity

  • Snyk14d

    Risk: MEDIUM · 2 issues

Provenance

Signed by skilld at ef8bcd5. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub 2 weeks ago.

Activeupdated 2 weeks ago

Capability

title
Base MCP Skill
version
0.1.0

Topics

  • MCP
  • base
  • blockchain
  • wallet
  • defi
  • ethereum
  • swaps
  • tokens
  • agent-tools

README badge

README badge for base/skills/base-mcp

What it does

Gives your AI assistant access to a Base Account wallet via the Base MCP server, enabling balance checks, token sends and swaps, message signing, x402 payments, batched contract calls, and transaction history. Includes optional plugins for Morpho, Moonwell, Uniswap, Avantis perpetuals, Virtuals agents, Aerodrome, and Bankr token launches.

Generated from the current SKILL.md.

Frequently asked

What do I need to install to use this skill?
You need the Base MCP server installed and connected. If Base MCP tools aren't available, visit https://docs.base.org/ai-agents/quickstart for installation steps specific to your platform.
What chains does Base MCP support?
The skill works across supported chains for wallet, portfolio, and transaction history. Individual plugins (Morpho, Moonwell, Uniswap, Avantis, Aerodrome, Bankr) are Base-only unless noted otherwise — Moonwell also supports Optimism.
Can I use this skill to sign transactions?
Yes. Base MCP supports signing messages and contract calls. Write operations that return an approval URL follow a specific approval flow — the skill will guide you through it.
What happens if I use a plugin that supports lending or leverage?
Plugins like Morpho, Moonwell, and Avantis can expose you to liquidation risk. The skill surfaces health factor and position data before risky actions, but you must review all details before approving any transaction.
Do I need to provide my wallet address at the start?
No. Wallet address and balance are only fetched when you ask for them or when a pending operation actually needs the address — like a token send or balance lookup.

Generated from the current SKILL.md. These answers refresh after source changes.